# ADLGen: Synthesizing Symbolic, Event-Triggered Sensor Sequences for Human Activity Modeling

arXiv: https://arxiv.org/abs/2505.17987 · HTML: https://mlsanity.com/paper/2505.17987/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 63 references that are in the map.
- First posted on arXiv 23 May 2025.

## Builds on (most cited first, 22 of 22)

- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs](https://mlsanity.com/paper/1706.02633/) (2017)
- [Transformer Hawkes Process](https://mlsanity.com/paper/2002.09291/) (2020)
- [AugGPT: Leveraging ChatGPT for Text Data Augmentation](https://mlsanity.com/paper/2302.13007/) (2023)
- [Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecasting](https://mlsanity.com/paper/2307.11494/) (2023)
- [Privacy Preserving Machine Learning: Threats and Solutions](https://mlsanity.com/paper/1804.11238/) (2018)
- [COT-GAN: Generating Sequential Data via Causal Optimal Transport](https://mlsanity.com/paper/2006.08571/) (2020)
- [STAR-Transformer: A Spatio-temporal Cross Attention Transformer for Human Action Recognition](https://mlsanity.com/paper/2210.07503/) (2022)
- [ElderSim: A Synthetic Data Generation Platform for Human Action Recognition in Eldercare Applications](https://mlsanity.com/paper/2010.14742/) (2020)
- [Constrained Diffusion Models via Dual Training](https://mlsanity.com/paper/2408.15094/) (2024)
- [A Systematic Assessment of OpenAI o1-Preview for Higher Order Thinking in Education](https://mlsanity.com/paper/2410.21287/) (2024)
- [Layout Agnostic Human Activity Recognition in Smart Homes through Textual Descriptions Of Sensor Triggers (TDOST)](https://mlsanity.com/paper/2405.12368/) (2024)
- [Measuring the quality of Synthetic data for use in competitions](https://mlsanity.com/paper/1806.11345/) (2018)
- [TimeLDM: Latent Diffusion Model for Unconditional Time Series Generation](https://mlsanity.com/paper/2407.04211/) (2024)
- [Machine Learning Techniques for Sensor-based Human Activity Recognition with Data Heterogeneity -- A Review](https://mlsanity.com/paper/2403.15422/) (2024)
- [Accurate Action Recommendation for Smart Home via Two-Level Encoders and Commonsense Knowledge](https://mlsanity.com/paper/2208.06089/) (2022)
- [Synthetic Tabular Data Generation for Imbalanced Classification: The Surprising Effectiveness of an Overlap Class](https://mlsanity.com/paper/2412.15657/) (2024)
- [A Quantitative Analysis of Activities of Daily Living: Insights into Improving Functional Independence with Assistive Robotics](https://mlsanity.com/paper/2104.03892/) (2021)
- [CGXplain: Rule-Based Deep Neural Network Explanations Using Dual Linear Programs](https://mlsanity.com/paper/2304.05207/) (2023)
- [Multimodal Generation of Novel Action Appearances for Synthetic-to-Real Recognition of Activities of Daily Living](https://mlsanity.com/paper/2208.01910/) (2022)
- [RNDiff: Rainfall nowcasting with Condition Diffusion Model](https://mlsanity.com/paper/2402.13737/) (2024)
- [Generative Resident Separation and Multi-label Classification for Multi-person Activity Recognition](https://mlsanity.com/paper/2404.07245/) (2024)

## Abstract (arXiv)

Real world collection of Activities of Daily Living data is challenging due to privacy concerns, costly deployment and labeling, and the inherent sparsity and imbalance of human behavior. We present ADLGen, a generative framework specifically designed to synthesize realistic, event triggered, and symbolic sensor sequences for ambient assistive environments. ADLGen integrates a decoder only Transformer with sign based symbolic temporal encoding, and a context and layout aware sampling mechanism to guide generation toward semantically rich and physically plausible sensor event sequences. To enhance semantic fidelity and correct structural inconsistencies, we further incorporate a large language model into an automatic generate evaluate refine loop, which verifies logical, behavioral, and temporal coherence and generates correction rules without manual intervention or environment specific tuning. Through comprehensive experiments with novel evaluation metrics, ADLGen is shown to outperform baseline generators in statistical fidelity, semantic richness, and downstream activity recognition, offering a scalable and privacy-preserving solution for ADL data synthesis.